FlowerPower 0.11.6.10__tar.gz → 0.11.6.12__tar.gz

{flowerpower-0.11.6.10/src/FlowerPower.egg-info → flowerpower-0.11.6.12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: FlowerPower
-Version: 0.11.6.10
+Version: 0.11.6.12
 Summary: A simple workflow framework. Hamilton + APScheduler = FlowerPower
 Author-email: "Volker L." <ligno.blades@gmail.com>
 Project-URL: Homepage, https://github.com/legout/flowerpower

{flowerpower-0.11.6.10 → flowerpower-0.11.6.12}/pyproject.toml

@@ -4,7 +4,7 @@ description = "A simple workflow framework. Hamilton + APScheduler = FlowerPower
 authors = [{ name = "Volker L.", email = "ligno.blades@gmail.com" }]
 readme = "README.md"
 requires-python = ">= 3.11"
-version = "0.11.6.10"
+version = "0.11.6.12"
 keywords = [
   "hamilton",
   "workflow",

{flowerpower-0.11.6.10 → flowerpower-0.11.6.12/src/FlowerPower.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: FlowerPower
-Version: 0.11.6.10
+Version: 0.11.6.12
 Summary: A simple workflow framework. Hamilton + APScheduler = FlowerPower
 Author-email: "Volker L." <ligno.blades@gmail.com>
 Project-URL: Homepage, https://github.com/legout/flowerpower

{flowerpower-0.11.6.10 → flowerpower-0.11.6.12}/src/flowerpower/fs/ext.py

@@ -953,8 +953,13 @@ def _read_parquet(
                 schemas = [t.schema for t in tables]
                 unified_schema = unify_schemas_pa(schemas)
                 tables = [cast_schema(t, unified_schema) for t in tables]
+
+            tables = [table for table in tables if table.num_rows > 0]
+            if not tables:
+                return unified_schema.empty_table()
+
             result = pa.concat_tables(
-                [table for table in tables if table.num_rows > 0],
+                tables,
                 promote_options="permissive",
             )
             # if opt_dtypes:
@@ -965,8 +970,12 @@ def _read_parquet(
             #    tables = opt_dtype_pa(tables, strict=False)
             return tables
         else:
-            return pa.concat_tables(
-                [table for table in tables if table.num_rows > 0],
+            tables = [table for table in tables if table.num_rows > 0]
+            if not tables:
+                return unified_schema.empty_table()
+
+            result = pa.concat_tables(
+                tables,
                 promote_options="permissive",
             )
     return tables
@@ -1088,8 +1097,11 @@ def _read_parquet_batches(
                 schemas = [t.schema for t in batch_tables]
                 unified_schema = unify_schemas_pa(schemas)
                 batch_tables = [cast_schema(t, unified_schema) for t in batch_tables]
+            batch_tables = [table for table in batch_tables if table.num_rows > 0]
+            if not batch_tables:
+                yield unified_schema.empty_table()
             batch_table = pa.concat_tables(
-                [table for table in batch_tables if table.num_rows > 0],
+                batch_tables,
                 promote_options="permissive",
             )
             # if opt_dtypes:

{flowerpower-0.11.6.10 → flowerpower-0.11.6.12}/src/flowerpower/plugins/io/helpers/polars.py

@@ -68,7 +68,7 @@ def _optimize_string_column(
     cleaned_expr = _clean_string_expr(col_name)
     non_null = series.drop_nulls().replace({"-": None, "": None, "None": None})
     if len(non_null) == 0:
-        return pl.col(col_name).cast(series.dtype)
+        return pl.col(col_name).cast(pl.Null())  # Fix: Cast to Null type
 
     stripped = non_null.str.strip_chars()
     lowercase = stripped.str.to_lowercase()
@@ -123,7 +123,7 @@ def _get_column_expr(
 
     # Handle all-null columns
     if series.is_null().all():
-        return pl.col(col_name).cast(series.dtype)
+        return pl.col(col_name).cast(pl.Null())
 
     # Process based on current type
     if series.dtype.is_numeric():

{flowerpower-0.11.6.10 → flowerpower-0.11.6.12}/src/flowerpower/plugins/io/helpers/pyarrow.py

@@ -272,7 +272,7 @@ def _optimize_string_array(
     if len(array) == 0:
         return pa.array([], type=pa.int8())
     if array.null_count == len(array):
-        return pa.array([None] * len(array), type=array.type)
+        return pa.array([None] * len(array), type=pa.null())
 
     # Clean string values
     cleaned_array = _clean_string_array(array)
@@ -342,7 +342,7 @@ def _process_column(
 
     # Handle all-null columns
     if array.null_count == len(array):
-        return pa.array([None] * len(array), type=array.type)
+        return pa.array([None] * len(array), type=pa.null())
 
     # Process based on current type
     if pa.types.is_floating(array.type) or pa.types.is_integer(array.type):